Talorys

# Fix list: Talorys

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/talorys, the October 2026 research run, assessed 12 October 2026. Grade F, 28.9 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Talorys: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Schema & documentation, 0 out of 100, up to 16.3 more on the total

Why it scored 0: Graded on the interface an outside agent can use, as GRADER.md asks. Talorys has none. Its /api routes are the web app's private backend, undocumented as an API, and need the owner's session cookie, an x-talorys-request header and a same-origin Origin, with no API key, MCP server or A2A endpoint. So the contract, description, typed-input and example lines score nothing (0 of 25, 0 of 20, 0 of 15, 0 of 15), which says nothing about the app for its owner. The docs are Markdown files in the repository with no llms.txt or served copies, which the Khoj and Aider dossiers scored 0 (0 of 10). The versioning and changelog line versions an agent interface, and with none there is nothing to version, so it scores nothing (0 of 15). We read it this way for every listing in this batch without an agent interface, and app release notes count under maintenance instead.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 2. Agent ergonomics, 0 out of 100, up to 16.3 more on the total

Why it scored 0: Graded on the interface an outside agent can use. Talorys has none, so context cost, pagination, errors, retries and defaults have nothing to score (0 on each line). This says nothing about the app for its owner. The reason is in the schema note.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 3. Security & auth, 8 out of 100, up to 16.1 more on the total

Why it scored 8: Graded on the interface an outside agent can use. With none for Talorys, the credential, least-privilege, injection and audit lines score nothing (0 of 30, 0 of 20, 0 of 15, 0 of 15), whatever the app does for its owner. The security programme line doesn't need an interface and is scored. For the record, docs/security.md documents a PBKDF2-hashed owner password, HMAC-stored session tokens, login lockouts with Retry-After, CSRF checks, a Worker with no public URL, destructive tools that need confirmation in the owner's latest message, read-only tools for scheduled runs, imported automations paused, and no shell or outbound HTTP tools. Security programme. SECURITY.md asks for private GitHub reports, aims to acknowledge within 3 business days and fix within 30, sets a scope that includes prompt injection causing unconfirmed writes, and docs/security.md sets out a threat model. An esbuild dev-dependency advisory was overridden on 11 October. No security.txt (there's no site), bug bounty, certification or published advisories (8 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 4. Reliability, 41 out of 100, up to 11.8 more on the total

Why it scored 41: Read with the local-software lines, as GRADER.md sets for Talorys and as the Goose and Aider dossiers read them. create-talorys on npm with Node.js 22 or later stated, deploying into the owner's Cloudflare account (20). The CI workflow runs lint, typecheck, build, unit tests, a pack test and Playwright end-to-end tests on pushes to main and on pull requests. GitHub refused our requests for run results, and the Goose dossier gave 18 for CI whose current state was unconfirmed (18 of 25). Open issues are unchecked. GitHub's issue pages and API refused our requests, and the clone shows only merged pull requests (12 of the 24 numbers used since 10 October), so the open reports couldn't be read. The brief scores an unchecked line as absent, and the repository may be fine on it (0, unchecked). Semver releases on npm (0.1.0 to 0.1.5) and two tags, with no changelog or breaking-change notes (3 of 15). 0.1.5, pre-1.0 (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 5. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: Read with the self-hosted rule, as the Khoj, Goose and Aider dossiers read it. No payment protocol (0). Free and MIT-licensed with nothing to buy, so 20, 20 and 20 on the last three lines. The README says it fits Cloudflare's Workers Free plan, and use beyond the included amounts on a paid Cloudflare plan is billed by Cloudflare, not Talorys.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 6. Transparency & trust, 52 out of 100, up to 4.2 more on the total

Made of editorial 77, provenance 27.

Why it scored 52: MIT (30). There's no vendor service, so no terms or privacy policy of its own. The README says Talorys has no telemetry, analytics or tracking and sends nothing to its developers, that data lives in a Durable Object in the owner's Cloudflare account, and that Cloudflare processes it, Workers AI inference on messages and memories included. The source makes no outbound calls beyond Cloudflare bindings and the installer turns Wrangler's metrics off, which agrees. Sessions expire after 30 days or 14 of inactivity, and retention at Cloudflare follows Cloudflare's terms (22 of 30). SECURITY.md says only the latest version gets fixes and migrations are append-only, with no deprecation policy (5 of 20). No telemetry, stated in the README and consistent with the code, so there's nothing to opt out of (20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Legal entity named: not found (0 of 20)
- Domain age: github.com, no registry record we could read (0 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 83 out of 100, up to 1.5 more on the total

Why it scored 83: create-talorys 0.1.5 published to npm on 12 October 2026 (30). Five releases since 10 October, 0.1.0 to 0.1.5 (20). Pull requests from outside contributors (at least five authors besides the maintainer) and Dependabot were merged on 11 and 12 October, the earliest within about two hours of their last commit. Issue replies couldn't be read. The Marmot dossier gave 15 where activity was visible and reply times weren't (15 of 25). Read as current official builds, as the Open WebUI and Goose dossiers read this line for local software. The npm installer tracks main and deploys the agent, with no other packages (12 of 15). A lockfile, current dependencies (TypeScript 6, Vitest 4), Dependabot security pull requests and an esbuild override for an advisory, with no dependabot.yml or audit workflow and CI results unseen, below Goose's 8 for a fuller toolchain (6 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: open issues and reply times, since GitHub's issue pages and API refused our requests. The reliability open-issues line scores 0 for that reason only.
- unchecked: whether CI passes on main, for the same reason.
- unchecked: GitHub star count.

## Weaknesses

- No API key, MCP server or A2A endpoint, and the /api routes need the owner's browser session.
- First released on 10 October 2026 and still pre-1.0 at 0.1.5.
- No changelog or breaking-change notes.
- No mail, calendar, booking, payment or messaging connections in the code.

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Run `npx create-talorys@latest` with Node.js 22 or later and a Cloudflare login or an API token with Workers, Pages and Workers AI permissions.
- Don't script the /api routes. They need the owner's session cookie and CSRF header and aren't documented for other callers.
- Update with `npx create-talorys@latest update`. Only the latest version gets security fixes.

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.